In the news
Catch production failures early with LangSmith Alerts
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangSmith launched Alerts to monitor LLM applications in production, triggering on error rate, latency, and feedback scores.
- Why it matters
- Engineers running LLM agents or applications in production who need early warning of failures or quality degradation.
- Watch out
- Alerts require existing production traces in LangSmith; future features like token usage alerts and relative thresholds are not yet available.
- latency
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.